Add sample files

data/z_animal.csv

@@ -0,0 +1,11 @@
+AnimalID,CommonName,ScientificName,Class,Order,Family,Habitat,ConservationStatus
+1,Lion,Panthera leo,Mammalia,Carnivora,Felidae,Savanna,Vulnerable
+2,Eagle,Aquila chrysaetos,Aves,Accipitriformes,Accipitridae,Mountains,Least Concern
+3,Dolphin,Tursiops truncatus,Mammalia,Cetacea,Delphinidae,Ocean,Least Concern
+4,Elephant,Loxodonta africana,Mammalia,Proboscidea,Elephantidae,Grassland,Vulnerable
+5,Tiger,Panthera tigris,Mammalia,Carnivora,Felidae,Forest,Endangered
+6,Penguin,Spheniscidae,Aves,Sphenisciformes,Spheniscidae,Antarctica,Least Concern
+7,Giraffe,Giraffa camelopardalis,Mammalia,Artiodactyla,Giraffidae,Savanna,Vulnerable
+8,Cheetah,Acinonyx jubatus,Mammalia,Carnivora,Felidae,Grassland,Vulnerable
+9,Panda,Ailuropoda melanoleuca,Mammalia,Carnivora,Ursidae,Forest,Endangered
+10,Kangaroo,Macropus rufus,Mammalia,Diprotodontia,Macropodidae,Grassland,Least Concern

data/z_employee.csv

@@ -0,0 +1,26 @@
+EmployeeID,FirstName,LastName,Email,Department,Salary
+101,John,Smith,john.smith@example.com,Finance,60000
+102,Emily,Johnson,emily.johnson@example.com,Marketing,55000
+103,Michael,Williams,michael.williams@example.com,HR,50000
+104,Susan,Anderson,susan.anderson@example.com,IT,65000
+105,David,Martin,david.martin@example.com,Sales,58000
+106,Linda,Davis,linda.davis@example.com,Finance,62000
+107,William,Miller,william.miller@example.com,Marketing,56000
+108,Sarah,Anderson,sarah.anderson@example.com,HR,51000
+109,Robert,Clark,robert.clark@example.com,IT,67000
+110,Karen,Wilson,karen.wilson@example.com,Sales,59000
+111,James,Brown,james.brown@example.com,Finance,61000
+112,Anna,Johnson,anna.johnson@example.com,Marketing,57000
+113,Christopher,Moore,christopher.moore@example.com,HR,52000
+114,Laura,White,laura.white@example.com,IT,68000
+115,Mark,Davis,mark.davis@example.com,Sales,60000
+116,Patricia,Jones,patricia.jones@example.com,Finance,63000
+117,Matthew,Taylor,matthew.taylor@example.com,Marketing,58000
+118,Jennifer,Young,jennifer.young@example.com,HR,53000
+119,Steven,Anderson,steven.anderson@example.com,IT,69000
+120,Elizabeth,Thomas,elizabeth.thomas@example.com,Sales,61000
+121,Kevin,Harris,kevin.harris@example.com,Finance,64000
+122,Deborah,Smith,deborah.smith@example.com,Marketing,59000
+123,Joseph,Walker,joseph.walker@example.com,HR,54000
+124,Cynthia,Jackson,cynthia.jackson@example.com,IT,70000
+125,Daniel,Hall,daniel.hall@example.com,Sales,62000

data/z_house.csv

@@ -0,0 +1,7 @@
+PropertyID,StreetAddress,City,State,ZipCode,NumberOfBedrooms,NumberOfBathrooms,SquareFootage,Price
+1,123 Main St,Los Angeles,CA,90001,3,2,1800,550000
+2,456 Elm St,New York,NY,10001,2,1,1200,750000
+3,789 Oak St,San Francisco,CA,94101,4,3,2500,950000
+4,101 Maple St,Boston,MA,02101,3,2.5,2000,680000
+5,202 Pine St,Miami,FL,33101,4,3.5,2700,820000
+6,303 Cedar St,Chicago,IL,60601,2,1,1100,450000

utils/load_csv.py

@@ -0,0 +1,23 @@
+import pandas as pd
+from utils.read_config import get_args
+def check_csv(upload_file):
+    df = pd.read_csv(upload_file)
+    return df
+
+# Function to load sample of dataset
+def load_sample(num_sample_records, sample_method, df, col_name):
+
+    sample_first_records = get_args("first_records")
+    sample_random_seed = get_args("random_seed")
+
+    num_sample_records = num_sample_records if num_sample_records <= sample_first_records else sample_first_records
+    
+    # Keep only required column
+    df = df[[col_name]]
+    if sample_method == "First":
+        df = df.iloc[:num_sample_records].copy().reset_index()
+    if sample_method == "Last":
+        df = df.iloc[-num_sample_records:].copy().reset_index()
+    if sample_method == "Random":
+        df = df.sample(num_sample_records, random_state=sample_random_seed).copy().reset_index()
+    return df